Neural Networks - Back Propogation












1












$begingroup$


The following code is my implementation of neural network (1 hidden layer) trying to predict some number based on input data.




  • Number of input node: 11

  • Number of nodes in hidden layer: 11

  • Number of nodes in output layer: 1


  • m: number of training examples, here = 4527


  • X: [11, m] matrix


  • y: [1, m] matrix


  • w1: weights associated from input layer to hidden layer


  • b1: bias vector associated from input layer to hidden layer


  • w2: weights associated from hidden layer to output layer


  • b2: bias vector associated from hidden layer to output layer


  • alpha: learning rate


  • ite: number of iteration, here = 10000


Since I'm trying to predict a continuous value output, I'm using sigmoid function in input layers and identity function in output layer



def propagate(X,y,w1,b1,w2,b2,alpha,ite):
assert(X.shape[0] == 11)
assert(y.shape[0] == 1)
assert(X.shape[1] == y.shape[1])
m = X.shape[1]
J = np.zeros(shape=(ite,1))
iteNo = np.zeros(shape=(ite,1))
for i in range(1,ite+1):
z1 = np.dot(w1,X) + b1
a1 = sigmoid(z1)
z2 = np.dot(w2,a1) + b2

dz2 = (z2-y)/m
dw2 = np.dot(dz2,a1.T)
db2 = np.sum(dz2, axis=1, keepdims=True)
dz1 = np.dot(w2.T,dz2)*derivative_of_sigmoid(z1)
dw1 = np.dot(dz1,X.T)
db1 = np.sum(dz1, axis=1, keepdims=True)

w2 = w2 - (alpha*dw2)
b2 = b2 - (alpha*db2)
w1 = w1 - (alpha*dw1)
b1 = b1 - (alpha*db1)

iteNo[i-1] = i
J[i-1] = np.dot((z2-y),(z2-y).T)/(2*m)

print(z2)
return w1,b1,w2,b2,iteNo,J


I have tried both the ways (With feature normalization and scaling & without) but my cost function varies as follows with respect number of iterations (Plotted J).



On $x$-axis: Number of iteration, On $y$-axis: Error $times 10^{12}$.
On x-axis: Number of iteration, On y-axis: Error * 10^12



Please help!










share|improve this question









New contributor




Chirag is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.







$endgroup$

















    1












    $begingroup$


    The following code is my implementation of neural network (1 hidden layer) trying to predict some number based on input data.




    • Number of input node: 11

    • Number of nodes in hidden layer: 11

    • Number of nodes in output layer: 1


    • m: number of training examples, here = 4527


    • X: [11, m] matrix


    • y: [1, m] matrix


    • w1: weights associated from input layer to hidden layer


    • b1: bias vector associated from input layer to hidden layer


    • w2: weights associated from hidden layer to output layer


    • b2: bias vector associated from hidden layer to output layer


    • alpha: learning rate


    • ite: number of iteration, here = 10000


    Since I'm trying to predict a continuous value output, I'm using sigmoid function in input layers and identity function in output layer



    def propagate(X,y,w1,b1,w2,b2,alpha,ite):
    assert(X.shape[0] == 11)
    assert(y.shape[0] == 1)
    assert(X.shape[1] == y.shape[1])
    m = X.shape[1]
    J = np.zeros(shape=(ite,1))
    iteNo = np.zeros(shape=(ite,1))
    for i in range(1,ite+1):
    z1 = np.dot(w1,X) + b1
    a1 = sigmoid(z1)
    z2 = np.dot(w2,a1) + b2

    dz2 = (z2-y)/m
    dw2 = np.dot(dz2,a1.T)
    db2 = np.sum(dz2, axis=1, keepdims=True)
    dz1 = np.dot(w2.T,dz2)*derivative_of_sigmoid(z1)
    dw1 = np.dot(dz1,X.T)
    db1 = np.sum(dz1, axis=1, keepdims=True)

    w2 = w2 - (alpha*dw2)
    b2 = b2 - (alpha*db2)
    w1 = w1 - (alpha*dw1)
    b1 = b1 - (alpha*db1)

    iteNo[i-1] = i
    J[i-1] = np.dot((z2-y),(z2-y).T)/(2*m)

    print(z2)
    return w1,b1,w2,b2,iteNo,J


    I have tried both the ways (With feature normalization and scaling & without) but my cost function varies as follows with respect number of iterations (Plotted J).



    On $x$-axis: Number of iteration, On $y$-axis: Error $times 10^{12}$.
    On x-axis: Number of iteration, On y-axis: Error * 10^12



    Please help!










    share|improve this question









    New contributor




    Chirag is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
    Check out our Code of Conduct.







    $endgroup$















      1












      1








      1





      $begingroup$


      The following code is my implementation of neural network (1 hidden layer) trying to predict some number based on input data.




      • Number of input node: 11

      • Number of nodes in hidden layer: 11

      • Number of nodes in output layer: 1


      • m: number of training examples, here = 4527


      • X: [11, m] matrix


      • y: [1, m] matrix


      • w1: weights associated from input layer to hidden layer


      • b1: bias vector associated from input layer to hidden layer


      • w2: weights associated from hidden layer to output layer


      • b2: bias vector associated from hidden layer to output layer


      • alpha: learning rate


      • ite: number of iteration, here = 10000


      Since I'm trying to predict a continuous value output, I'm using sigmoid function in input layers and identity function in output layer



      def propagate(X,y,w1,b1,w2,b2,alpha,ite):
      assert(X.shape[0] == 11)
      assert(y.shape[0] == 1)
      assert(X.shape[1] == y.shape[1])
      m = X.shape[1]
      J = np.zeros(shape=(ite,1))
      iteNo = np.zeros(shape=(ite,1))
      for i in range(1,ite+1):
      z1 = np.dot(w1,X) + b1
      a1 = sigmoid(z1)
      z2 = np.dot(w2,a1) + b2

      dz2 = (z2-y)/m
      dw2 = np.dot(dz2,a1.T)
      db2 = np.sum(dz2, axis=1, keepdims=True)
      dz1 = np.dot(w2.T,dz2)*derivative_of_sigmoid(z1)
      dw1 = np.dot(dz1,X.T)
      db1 = np.sum(dz1, axis=1, keepdims=True)

      w2 = w2 - (alpha*dw2)
      b2 = b2 - (alpha*db2)
      w1 = w1 - (alpha*dw1)
      b1 = b1 - (alpha*db1)

      iteNo[i-1] = i
      J[i-1] = np.dot((z2-y),(z2-y).T)/(2*m)

      print(z2)
      return w1,b1,w2,b2,iteNo,J


      I have tried both the ways (With feature normalization and scaling & without) but my cost function varies as follows with respect number of iterations (Plotted J).



      On $x$-axis: Number of iteration, On $y$-axis: Error $times 10^{12}$.
      On x-axis: Number of iteration, On y-axis: Error * 10^12



      Please help!










      share|improve this question









      New contributor




      Chirag is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.







      $endgroup$




      The following code is my implementation of neural network (1 hidden layer) trying to predict some number based on input data.




      • Number of input node: 11

      • Number of nodes in hidden layer: 11

      • Number of nodes in output layer: 1


      • m: number of training examples, here = 4527


      • X: [11, m] matrix


      • y: [1, m] matrix


      • w1: weights associated from input layer to hidden layer


      • b1: bias vector associated from input layer to hidden layer


      • w2: weights associated from hidden layer to output layer


      • b2: bias vector associated from hidden layer to output layer


      • alpha: learning rate


      • ite: number of iteration, here = 10000


      Since I'm trying to predict a continuous value output, I'm using sigmoid function in input layers and identity function in output layer



      def propagate(X,y,w1,b1,w2,b2,alpha,ite):
      assert(X.shape[0] == 11)
      assert(y.shape[0] == 1)
      assert(X.shape[1] == y.shape[1])
      m = X.shape[1]
      J = np.zeros(shape=(ite,1))
      iteNo = np.zeros(shape=(ite,1))
      for i in range(1,ite+1):
      z1 = np.dot(w1,X) + b1
      a1 = sigmoid(z1)
      z2 = np.dot(w2,a1) + b2

      dz2 = (z2-y)/m
      dw2 = np.dot(dz2,a1.T)
      db2 = np.sum(dz2, axis=1, keepdims=True)
      dz1 = np.dot(w2.T,dz2)*derivative_of_sigmoid(z1)
      dw1 = np.dot(dz1,X.T)
      db1 = np.sum(dz1, axis=1, keepdims=True)

      w2 = w2 - (alpha*dw2)
      b2 = b2 - (alpha*db2)
      w1 = w1 - (alpha*dw1)
      b1 = b1 - (alpha*db1)

      iteNo[i-1] = i
      J[i-1] = np.dot((z2-y),(z2-y).T)/(2*m)

      print(z2)
      return w1,b1,w2,b2,iteNo,J


      I have tried both the ways (With feature normalization and scaling & without) but my cost function varies as follows with respect number of iterations (Plotted J).



      On $x$-axis: Number of iteration, On $y$-axis: Error $times 10^{12}$.
      On x-axis: Number of iteration, On y-axis: Error * 10^12



      Please help!







      machine-learning python neural-network






      share|improve this question









      New contributor




      Chirag is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.











      share|improve this question









      New contributor




      Chirag is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      share|improve this question




      share|improve this question








      edited yesterday









      Siong Thye Goh

      1,122418




      1,122418






      New contributor




      Chirag is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      asked yesterday









      ChiragChirag

      61




      61




      New contributor




      Chirag is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.





      New contributor





      Chirag is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






      Chirag is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






















          0






          active

          oldest

          votes











          Your Answer





          StackExchange.ifUsing("editor", function () {
          return StackExchange.using("mathjaxEditing", function () {
          StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
          StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
          });
          });
          }, "mathjax-editing");

          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "557"
          };
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function() {
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled) {
          StackExchange.using("snippets", function() {
          createEditor();
          });
          }
          else {
          createEditor();
          }
          });

          function createEditor() {
          StackExchange.prepareEditor({
          heartbeatType: 'answer',
          autoActivateHeartbeat: false,
          convertImagesToLinks: false,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: null,
          bindNavPrevention: true,
          postfix: "",
          imageUploader: {
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          },
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });






          Chirag is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f45965%2fneural-networks-back-propogation%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          0






          active

          oldest

          votes








          0






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes








          Chirag is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          Chirag is a new contributor. Be nice, and check out our Code of Conduct.













          Chirag is a new contributor. Be nice, and check out our Code of Conduct.












          Chirag is a new contributor. Be nice, and check out our Code of Conduct.
















          Thanks for contributing an answer to Data Science Stack Exchange!


          • Please be sure to answer the question. Provide details and share your research!

          But avoid



          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.


          Use MathJax to format equations. MathJax reference.


          To learn more, see our tips on writing great answers.




          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f45965%2fneural-networks-back-propogation%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          Popular posts from this blog

          How to label and detect the document text images

          Vallis Paradisi

          Tabula Rosettana